Skip to content

Tutorials

Scikit-eo provides a rich suite of algorithms specifically designed for environmental studies. These include statistical analysis, machine learning, deep learning, data fusion and spatial analysis. Researchers can leverage these tools to explore patterns, relationships, and trends within their datasets, to uncover complex land or forest degradation or mapping and classify the land cover, and generate insightful visualizations, among others tools.

Scikit-eo tutorials notebooks

Google Colab Youtube

Remote sensing tools of scikit-eo can be mainly grouped into 3 sets.

Tools for remote sensing data analysis

1 Machine Learning.ipynb

2 Estimated area and uncertainty in Machine Learning.ipynb

3 Calibrating supervised classification in Remote Sensing.ipynb

4 Kmeans classification.ipynb

5 Fusion of radar and optical images.ipynb

6 Spectral Mixture Analysis.ipynb

7 Principal Components Analysis.ipynb

8 Tasseled-Cap Transformation.ipynb

9 Linear trend analysis.ipynb

10 Logistic regression in remote sensing.ipynb

11 Deep Learning Classification FullyConnected.ipynb

Tools for satellite image preprocessing

12 Atmospheric Correction.ipynb

13 Clipping an image.ipynb

14 Writing a satellite image (raster).ipynb

Tools for satellite image visualizations

15 Plot an satellite image in RGB.ipynb

16 Plot a satellite image histogram.ipynb